Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    punctuation and conjunctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    contrast or comparison

    np_acts-logits-general · gemini-2.0-flash

    introducing contrast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    expandindo
    -0.59
     estekak
    -0.59
    GEBURTSDATUM
    -0.58
    BorderFactory
    -0.58
     userSchema
    -0.54
     mergeFrom
    -0.52
     وتسجيلات
    -0.51
     Siamo
    -0.50
     IDisposable
    -0.50
    ButtonStyle
    -0.50
    POSITIVE LOGITS
    Whereas
    0.78
     Whereas
    0.76
     whereas
    0.73
    Conversely
    0.73
     meanwhile
    0.71
     Conversely
    0.71
     Sedangkan
    0.68
     conversely
    0.68
    whereas
    0.65
     sedangkan
    0.64
    Act Density 0.380%

    No Known Activations